Show simple item record

dc.contributor.authorShanableh, Tamer
dc.contributor.authorAssaleh, Khaled
dc.contributor.authorAl-Rousan, Mohammad
dc.date.accessioned2021-03-14T09:59:05Z
dc.date.available2021-03-14T09:59:05Z
dc.date.issued2007
dc.identifier.citationT. Shanableh, K. Assaleh and M. Al-Rousan, "Spatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Language," in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 37, no. 3, pp. 641-650, June 2007, doi: 10.1109/TSMCB.2006.889630.en_US
dc.identifier.issn1941-0492
dc.identifier.urihttp://hdl.handle.net/11073/21363
dc.description.abstractThis paper presents various spatio-temporal feature-extraction techniques with applications to online and offline recognitions of isolated Arabic Sign Language gestures. The temporal features of a video-based gesture are extracted through forward, backward, and bidirectional predictions. The prediction errors are thresholded and accumulated into one image that represents the motion of the sequence. The motion representation is then followed by spatial-domain feature extractions. As such, the temporal dependencies are eliminated and the whole video sequence is represented by a few coefficients. The linear separability of the extracted features is assessed, and its suitability for both parametric and nonparametric classification techniques is elaborated upon. The proposed feature-extraction scheme was complemented by simple classification techniques, namely, K nearest neighbor (KNN) and Bayesian, i.e., likelihood ratio, classifiers. Experimental results showed classification performance ranging from 97% to 100% recognition rates. To validate our proposed technique, we have conducted a series of experiments using the classical way of classifying data with temporal dependencies, namely, hidden Markov models (HMMs). Experimental results revealed that the proposed feature-extraction scheme combined with simple KNN or Bayesian classification yields comparable results to the classical HMM-based scheme. Moreover, since the proposed scheme compresses the motion information of an image sequence into a single image, it allows for using simple classification techniques where the temporal dimension is eliminated. This is actually advantageous for both computational and storage requirements of the classifier.en_US
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.urihttps://doi.org/10.1109/TSMCB.2006.889630en_US
dc.subjectFeature extractionen_US
dc.subjectMotion analysisen_US
dc.subjectPattern classificationen_US
dc.subjectVisual languagesen_US
dc.titleSpatio-Temporal Feature-Extraction Techniques for Isolated Gesture Recognition in Arabic Sign Languageen_US
dc.typePeer-Revieweden_US
dc.typeArticleen_US
dc.typePostprinten_US
dc.identifier.doi10.1109/TSMCB.2006.889630


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record